Boxplots (simple and clustered)
Summarizes distributions with the median, Tukey hinges (box), whiskers and individually labelled outliers (○) and extremes (*), each marked with its case number.
Menu: Graphs → More charts → Boxplot (simple / clustered)…
When should I use it?
- Comparing groups and spotting unusual cases.
- Checking skew and spread before a t test or ANOVA.
What are the assumptions?
- Scale variables.
How do I run it in StatLab?
- Choose one or more variables.
- Optionally add a category axis and a cluster variable.
How do I read the output?
| Output | Meaning |
|---|---|
| Box | Middle half of the data (Tukey hinges, as SPSS Explore). |
| Whiskers | Furthest values within 1.5 box lengths. |
| ○ / * | Outliers beyond 1.5 and extremes beyond 3 box lengths, labelled by case number. |
Worked example
On the practice survey dataset (File → Sample dataset), this command — which the dialog's Paste button also produces — runs the procedure:
PROC vizBoxplot /y=(score age) /x='' /color='' /showMean=NO.
Computed by StatLab's validated procedure code when this page was built. The example only illustrates the steps; choose variables that fit your own research question.
What are common mistakes?
- Deleting outliers just because they are drawn — check them first.
- Comparing boxplots from very small groups (n < 5).